NVIDIA/earth2studio

Open-source deep-learning framework for exploring, building and deploying AI weather/climate workflows.

80
/ 100
Verified

This tool helps meteorologists, climate scientists, and environmental researchers explore, build, and deploy AI models for weather and climate prediction. You can input current atmospheric data from sources like GFS or IFS, choose from a large collection of pre-trained AI models (like FourCastNet3, AIFS, or GraphCast), and then generate future weather forecasts or climate simulations. It's designed for professionals who need to quickly run and customize advanced AI-driven Earth system models.

694 stars. Actively maintained with 42 commits in the last 30 days. Available on PyPI.

Use this if you need to rapidly develop and run AI models for weather forecasting or climate research, and want to easily swap out different AI models or data sources.

Not ideal if you are looking for a simple, out-of-the-box weather app for daily personal use rather than a customizable AI modeling framework.

weather-forecasting climate-modeling atmospheric-science environmental-research geospatial-analysis
Maintenance 20 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 25 / 25

How are scores calculated?

Stars

694

Forks

155

Language

Python

License

Apache-2.0

Last pushed

Mar 12, 2026

Commits (30d)

42

Dependencies

18

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/NVIDIA/earth2studio"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.